SOTAVerified

Diversity

Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1851–1860 of 9051 papers

TitleStatusHype
Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial RobustnessCode0
Improving End-to-End Sequential Recommendations with Intent-aware DiversificationCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Improving Generalization with Domain Convex GameCode0
Complex Locomotion Skill Learning via Differentiable PhysicsCode0
Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQLCode0
Improving Diversity of Commonsense Generation by Large Language Models via In-Context LearningCode0
Improving Screening Processes via Calibrated Subset SelectionCode0
Complete 3D Scene Parsing from an RGBD ImageCode0
Improving Adversarial Robustness via Decoupled Visual Representation MaskingCode0
Show:102550
← PrevPage 186 of 906Next →

No leaderboard results yet.